Abstract In human–robot cooperation, the information interaction plays a key role. Most of the information interaction rely on Border Gateway Protocol (BGP), which is a vital route protocol on networks. However, the BGP is susceptible to the prefix interception attacks because the rightful origin of each prefix cannot be verified in BGP. For this reason, we propose a novel and effective route selection method against prefix interception attacks, which combines the resilience of routers and the historical performance of routers to choose a secure route. Moreover, we estimate the performance of BGP by introducing the definition of resilience and the historical performance of routers via online learning against the prefix interception attack. Furthermore, we analyze the bound of regret and obtain O ( T ) regret, where T denotes the time horizon. In addition, the proposed method is verified both on synthetic data and network simulations. The results show that the proposed method has more resilience against prefix interception attacks than Counter-Raptor.

中文翻译：

---

通过在线学习防范前缀拦截攻击

摘要 在人机合作中，信息交互起着关键作用。大多数信息交互依赖于边界网关协议（BGP），它是网络上重要的路由协议。然而，BGP 容易受到前缀拦截攻击，因为在 BGP 中无法验证每个前缀的合法来源。为此，我们提出了一种新颖有效的路由选择方法来对抗前缀拦截攻击，结合路由器的弹性和路由器的历史性能来选择安全路由。此外，我们通过对前缀拦截攻击的在线学习，通过引入弹性的定义和路由器的历史性能来估计BGP的性能。此外，我们分析遗憾的界限并获得 O ( T ) 遗憾，其中 T 表示时间范围。此外，所提出的方法在合成数据和网络模拟上都得到了验证。结果表明，与 Counter-Raptor 相比，所提出的方法对前缀拦截攻击具有更强的弹性。